@inproceedings{caines-etal-2016-crowdsourcing,
title = "Crowdsourcing a Multi-lingual Speech Corpus: Recording, Transcription and Annotation of the {C}rowd{IS} Corpora",
author = "Caines, Andrew and
Bentz, Christian and
Graham, Calbert and
Polzehl, Tim and
Buttery, Paula",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1340",
pages = "2145--2152",
abstract = "We announce the release of the CROWDED CORPUS: a pair of speech corpora collected via crowdsourcing, containing a native speaker corpus of English (CROWDED{\_}ENGLISH), and a corpus of German/English bilinguals (CROWDED{\_}BILINGUAL). Release 1 of the CROWDED CORPUS contains 1000 recordings amounting to 33,400 tokens collected from 80 speakers and is freely available to other researchers. We recruited participants via the Crowdee application for Android. Recruits were prompted to respond to business-topic questions of the type found in language learning oral tests. We then used the CrowdFlower web application to pass these recordings to crowdworkers for transcription and annotation of errors and sentence boundaries. Finally, the sentences were tagged and parsed using standard natural language processing tools. We propose that crowdsourcing is a valid and economical method for corpus collection, and discuss the advantages and disadvantages of this approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="caines-etal-2016-crowdsourcing">
<titleInfo>
<title>Crowdsourcing a Multi-lingual Speech Corpus: Recording, Transcription and Annotation of the CrowdIS Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Caines</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Bentz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Calbert</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Polzehl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paula</namePart>
<namePart type="family">Buttery</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We announce the release of the CROWDED CORPUS: a pair of speech corpora collected via crowdsourcing, containing a native speaker corpus of English (CROWDED_ENGLISH), and a corpus of German/English bilinguals (CROWDED_BILINGUAL). Release 1 of the CROWDED CORPUS contains 1000 recordings amounting to 33,400 tokens collected from 80 speakers and is freely available to other researchers. We recruited participants via the Crowdee application for Android. Recruits were prompted to respond to business-topic questions of the type found in language learning oral tests. We then used the CrowdFlower web application to pass these recordings to crowdworkers for transcription and annotation of errors and sentence boundaries. Finally, the sentences were tagged and parsed using standard natural language processing tools. We propose that crowdsourcing is a valid and economical method for corpus collection, and discuss the advantages and disadvantages of this approach.</abstract>
<identifier type="citekey">caines-etal-2016-crowdsourcing</identifier>
<location>
<url>https://aclanthology.org/L16-1340</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>2145</start>
<end>2152</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Crowdsourcing a Multi-lingual Speech Corpus: Recording, Transcription and Annotation of the CrowdIS Corpora
%A Caines, Andrew
%A Bentz, Christian
%A Graham, Calbert
%A Polzehl, Tim
%A Buttery, Paula
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F caines-etal-2016-crowdsourcing
%X We announce the release of the CROWDED CORPUS: a pair of speech corpora collected via crowdsourcing, containing a native speaker corpus of English (CROWDED_ENGLISH), and a corpus of German/English bilinguals (CROWDED_BILINGUAL). Release 1 of the CROWDED CORPUS contains 1000 recordings amounting to 33,400 tokens collected from 80 speakers and is freely available to other researchers. We recruited participants via the Crowdee application for Android. Recruits were prompted to respond to business-topic questions of the type found in language learning oral tests. We then used the CrowdFlower web application to pass these recordings to crowdworkers for transcription and annotation of errors and sentence boundaries. Finally, the sentences were tagged and parsed using standard natural language processing tools. We propose that crowdsourcing is a valid and economical method for corpus collection, and discuss the advantages and disadvantages of this approach.
%U https://aclanthology.org/L16-1340
%P 2145-2152
Markdown (Informal)
[Crowdsourcing a Multi-lingual Speech Corpus: Recording, Transcription and Annotation of the CrowdIS Corpora](https://aclanthology.org/L16-1340) (Caines et al., LREC 2016)
ACL